How to choose the right type of data visualization
Summary - Knowing how to read, work with, and visualize data is a necessary skill to have in today's market. This guide walks you through the common data visualizations that help you prove your performance and act on decisions.
Data literacy is becoming a must-have skill set.
There’s definitely a lot of data available to us, but making sense of it can be a challenge. It’s easy to think that choosing the right kind of data visualization to uncover hidden insights or create an awesome dashboard can be a bit of a black art.
If you need to become a data wizard - and fast - here’s a guide to some common data visualization techniques you need to know. Once you have a few of these under your belt, you’ll be able to use evidence to prove your performance and action important decisions.
Comparing data over time
Data Viz 101 starts with the ability to compare metric performance over time. Being able to point out trends in your data or compare current performance with that of a previous time period is gold. All decision makers need this in their toolkit.
Here’s a few basic chart types you can use to understand how your key metrics are trending over time.
Line charts show trends or progress over a period of time. Use a line chart to show how a continuous metric, like revenue, changes with time. You can plot a metric like revenue as a cumulative value, or, show it for each time period.
By adding a trend line - like a moving average or linear trend - you can smooth out the variability in your data and get a better sense for what’s going on. Interested in investigating short vs long term trends? You can isolate a particular time period to look at using a data selection filter.
Often, you’ll know something happened - like a decision was made or a change was implemented in your system on a certain date. So being able to see how the trend changed as of a particular date is really valuable. Showing the performance of your metric compared to the previous period overlayed on the same chart is another effective way to do this.
Indicators are useful for an at a glance view of a metric you need to keep track of. An indicator is simply a number showing the current value of whichever performance metric you’re tracking. To make it more useful, add a comparison to the previous time period to show whether your metric is tracking up or down.
Some people like to get fancy with indicators and use gauges or tickers. They present the same type of information, just in a different visual way.
A column chart is helpful for looking at data over time and comparing how different items or parts of your business performed relative to one another. You can break things down into different components on a column chart to see which one is growing the fastest or contributing the most.
I like using a stacked bar to compare a lot of different items. Outliers in the data for different time periods are immediately visible and then it’s helpful to use an interactive visualization tool to be able to filter and change the view to a line chart to get a better picture of how those items are trending over time.
Show how the parts of something contribute to the whole
More than just trends over time, your metric values are probably made up of different components or parts. Revenue, for example, might be derived from multiple products or types of sales leads. Being able to visualize how the different pieces contribute to the overall performance is the next step. The stacked bar chart above is one example of this kind of analysis.
An area chart is very similar to a line graph but may do a better job at highlighting the relative differences between items. Use an area chart when you want to see how different items stack up or contribute to the whole.
Pie charts show the composition of something you’re interested in, for a particular time period. The segments in a pie represent the % of the total value, where the total of all segments adds up to 100%.
Waterfall charts illustrate how a value is composed of its parts. It can also illustrate positive or negative contributions to the overall value. Use a waterfall chart when you want to see how different parts contribute to the overall total.
A treemap is a visual tool that can be used to break down the relationships between multiple variables in your data. They can be used strictly as a presentation vehicle to show how your products roll up into different categories, for example. A treemap can be broken down into 2-3 different layers to show the hierarchical relationship between items.
Understanding relationships between multiple variables
The next couple of charts are really useful for making big decisions or presenting evidence to build a case. They may not be charts that you use on an everyday basis, but you should know how to use them because they’ll make you super effective at pulling together different data to present a well informed picture of your business. They’re also useful for analyzing large amounts of data to highlight areas that need attention.
Heatmaps are everywhere these days. A heatmap is useful for highlighting outliers in your data that may need more analysis. It shows the relative “heat” for the 2 items you choose for the x and y axis. The variable you choose for the color coding acts like a scoring system. This variable provides relative information that can be used to highlight “good” or “weak” performance or a high to low scoring factor. Revenue or units sold can also be used as the variable to highlight above average or weak results.
Radar or Spider Chart
A radar chart is useful for understanding the relative differences between items in your data. Radar charts make it easy to compare multiple items and see if there are differences that may be worth further investigation.
Most of the examples above are more insightful when you can see the changes happening on the fly as you apply a different filter or look over a different date range.
Data visualizations that are created for status updates like regular reports are usually designed to be pretty static in nature. You might have a global date range picker on your report or the ability to change a couple of filters. Choosing a data visualization tool that gives you the option to dig deeper into your data with free-form data exploration (like Klipfolio) will give you the best of both worlds.